Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Pandas code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جب
    -0.07
    형
    -0.07
     Wage
    -0.07
    ewis
    -0.06
    ه
    -0.06
    -auth
    -0.06
    kan
    -0.06
    国
    -0.06
    衩
    -0.06
    icult
    -0.06
    POSITIVE LOGITS
    Υ
    0.07
     компании
    0.07
     facilitates
    0.07
     posted
    0.07
     allegedly
    0.07
    今天
    0.07
    userInfo
    0.07
    周围
    0.07
    cams
    0.07
    _feat
    0.07
    Act Density 0.011%

    No Known Activations